CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/public/deep-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a clear, actionable, well-sequenced research methodology with strong validation checkpoints. It is somewhat verbose with overlapping restatements and is monolithic rather than progressively disclosed across files.

Suggestions

Merge the redundant 'Core Principle', 'Quality Bar', 'Common Mistakes', and 'Output' sections into a single concise checklist to remove repeated 'research thoroughly' messaging.

Split the detailed 'Search Strategy Tips' (query patterns and temporal-aware table) into a referenced file (e.g., references/QUERY_PATTERNS.md) and keep SKILL.md as an overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly operational guidance rather than concept-explanation, but verbose: 'Core Principle', 'Quality Bar', 'Common Mistakes', and 'Output' all restate 'do thorough research before generating content'; not level 3 because the redundancy could be trimmed without losing clarity.

2 / 3

Actionability

For an instruction-only skill it gives concrete, specific guidance: executable query templates with ✅/❌ examples, a temporal-precision table mapping user intent to query form, and a Phase-4 checklist; absence of code is not penalized here.

3 / 3

Workflow Clarity

A clearly sequenced four-phase workflow with an explicit validation checkpoint (Phase 4 synthesis checklist) and a feedback loop ('If any answer is NO, continue researching before generating content').

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a well-organized single document, but it is a monolithic 190-line file with all content inline; not level 3 because nothing is split off despite length, and not level 1 because sections are clearly headed and navigable.

2 / 3

Total

10

/

12

Passed

Description

72%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states both capability and explicit trigger conditions with strong natural-language keywords. Its main weaknesses are second-person voice (a specificity penalty) and a broad scope that risks overlapping the built-in WebSearch.

Suggestions

Rewrite in third person ('Conducts systematic multi-angle web research...') to remove the second-person specificity penalty.

Replace the abstract 'multi-angle research methodology' with one or two concrete actions (e.g., 'runs multi-angle searches, fetches full sources, and cross-checks claims') to lift specificity.

Narrow the trigger scope or add a distinguishing clause (e.g., 'instead of WebSearch when a single query is insufficient') to reduce conflict risk with the built-in WebSearch.

DimensionReasoningScore

Specificity

It names the web-research domain and 'multi-angle research methodology' but lists no concrete actions (cf. 'extract, fill, merge'), and uses second-person voice ('Use this skill', 'Use this proactively'), which the guidelines penalize by reducing specificity by 1; not level 2 because it never enumerates specific actions.

1 / 3

Completeness

Clearly answers what ('Provides systematic multi-angle research methodology instead of single superficial searches') and when (explicit 'Trigger on queries like...' and 'Use this proactively when the user's question needs online information').

3 / 3

Trigger Term Quality

Natural query forms users would actually say are well covered: 'what is X', 'explain X', 'compare X and Y', 'research X', plus 'before content generation tasks'; not below 3 because these are exactly the phrasings a user would utter.

3 / 3

Distinctiveness Conflict Risk

It carves a niche ('instead of WebSearch') but the 'ANY question requiring web research' scope and generic 'what is X' triggers overlap the built-in WebSearch and other research skills; not level 3 because the triggers are broad enough to invite conflicts.

2 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.